Learning the energy curvature versus particle number in approximate density functionals

Abstract

The average energy curvature as a function of the particle number is a molecule-specific quantity, which measures the deviation of a given functional from the exact conditions of density functional theory (DFT). Related to the lack of derivative discontinuity in approximate exchange-correlation potentials, the information about the curvature has been successfully used to restore the physical meaning of Kohn-Sham orbital eigenvalues and to develop non-empirical tuning and correction schemes for density functional approximations. In this work, we propose the construction of a machine-learning framework targeting the average energy curvature between the neutral and the radical cation state of thousands of small organic molecules (QM7 database). The applicability of the model is demonstrated in the context of system-specific gamma-tuning of the LC-$\omega$PBE functional and validated against the molecular first ionization potentials at equation-of-motion (EOM) coupled-cluster references. In addition, we propose a local version of the non-linear regression model and demonstrate its transferability and predictive power by determining the optimal range-separation parameter for two large molecules relevant to the field of hole-transporting materials. Finally, we explore the underlying structure of the QM7 database with the t-SNE dimensionality-reduction algorithm and identify structural and compositional patterns that promote the deviation from the piecewise linearity condition.

References in corpus (35)

• Scikit-learn: Machine Learning in Python
• A linear response approach to the calculation of the effective interaction parameters in the LDA+U method
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Localization and delocalization errors in density functional theory and implications for band-gap prediction
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• By-passing the Kohn-Sham equations with machine learning
• Machine learning prediction errors better than DFT accuracy
• Fractional charge perspective on the band-gap in density-functional theory
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Alchemical and structural distribution based representation for improved QML
• Quasiparticle spectra from a non-empirical optimally-tuned range-separated hybrid density functional
• A Transferable Machine-Learning Model of the Electron Density
• Koopmans' condition for density-functional theory
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• The discontinuous nature of the exchange-correlation functional -- critical for strongly correlated systems
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Piecewise Linearity of Approximate Density Functionals Revisited: Implications for Frontier Orbital Energies
• Delocalization errors in density functional theory are essentially quadratic in fractional occupation number
• The derivative discontinuity of the exchange-correlation functional
• Transferable atomic multipole machine learning models for small organic molecules
• Towards quantifying the role of exact exchange in predictions of transition metal complex properties
• Fundamental gaps with approximate density functionals: the derivative discontinuity revealed from ensemble considerations
• Where Does the Density Localize? Convergent Behavior for Global Hybrids, Range Separation, and DFT+U
• Restoration of the Derivative Discontinuity in Kohn-Sham Density Functional Theory: An Efficient Scheme for Energy Gap Correction
• The derivative discontinuity in the strong-interaction limit of density functional theory
• Elimination of the asymptotic fractional dissociation problem in Kohn-Sham density functional theory using the ensemble-generalization approach
• Effect of ensemble generalization on the highest-occupied Kohn-Sham eigenvalue
• The fundamentals of quantum machine learning

Cited by in corpus (1)

• Improved accuracy and transferability of molecular-orbital-based machine learning: Organics, transition-metal complexes, non-covalent interactions, and transition states